Re: [PATCH v4] mm: swap: async free swap slot cache entries

[Tim Chen]

On Wed, 2024-02-14 at 17:02 -0800, Chris Li wrote:
> We discovered that 1% swap page fault is 100us+ while 50% of
> the swap fault is under 20us.
> 
> Further investigation shows that a large portion of the time
> spent in the free_swap_slots() function for the long tail case.
> 
> The percpu cache of swap slots is freed in a batch of 64 entries
> inside free_swap_slots(). These cache entries are accumulated
> from previous page faults, which may not be related to the current
> process.
> 
> Doing the batch free in the page fault handler causes longer
> tail latencies and penalizes the current process.
> 
> When the swap cache slot is full, schedule async free cached
> swap slots in a work queue, before the next swap fault comes in.
> If the next swap fault comes in very fast, before the async
> free gets a chance to run. It will directly free all the swap
> cache in the swap fault the same way as previously.
> 
> Testing:
> 
> Chun-Tse did some benchmark in chromebook, showing that
> zram_wait_metrics improve about 15% with 80% and 95% confidence.
> 
> I recently ran some experiments on about 1000 Google production
> machines. It shows swapin latency drops in the long tail
> 100us - 500us bucket dramatically.
> 
> platform	(100-500us)	 	(0-100us)
> A		1.12% -> 0.36%		98.47% -> 99.22%
> B		0.65% -> 0.15%		98.96% -> 99.46%
> C		0.61% -> 0.23%		98.96% -> 99.38%
> 
> Signed-off-by: Chris Li <chrisl@xxxxxxxxxx>

Reviewed-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>

> ---
> Changes in v4:
> - Remove the sysfs interface file, according the feedback.
> - Move the full condition test inside the spinlock.
> - Link to v3: https://lore.kernel.org/r/20240213-async-free-v3-1-b89c3cc48384@xxxxxxxxxx
> 
> Changes in v3:
> - Address feedback from Tim Chen, direct free path will free all swap slots.
> - Add /sys/kernel/mm/swap/swap_slot_async_fee to enable async free. Default is off.
> - Link to v2: https://lore.kernel.org/r/20240131-async-free-v2-1-525f03e07184@xxxxxxxxxx
> 
> Changes in v2:
> - Add description of the impact of time changing suggest by Ying.
> - Remove create_workqueue() and use schedule_work()
> - Link to v1: https://lore.kernel.org/r/20231221-async-free-v1-1-94b277992cb0@xxxxxxxxxx
> ---
>  include/linux/swap_slots.h |  1 +
>  mm/swap_slots.c            | 20 ++++++++++++++++++++
>  2 files changed, 21 insertions(+)
> 
> diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h
> index 15adfb8c813a..67bc8fa30d63 100644
> --- a/include/linux/swap_slots.h
> +++ b/include/linux/swap_slots.h
> @@ -19,6 +19,7 @@ struct swap_slots_cache {
>  	spinlock_t	free_lock;  /* protects slots_ret, n_ret */
>  	swp_entry_t	*slots_ret;
>  	int		n_ret;
> +	struct work_struct async_free;
>  };
>  
>  void disable_swap_slots_cache_lock(void);
> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
> index 0bec1f705f8e..23dc04bce9ca 100644
> --- a/mm/swap_slots.c
> +++ b/mm/swap_slots.c
> @@ -44,6 +44,7 @@ static DEFINE_MUTEX(swap_slots_cache_mutex);
>  static DEFINE_MUTEX(swap_slots_cache_enable_mutex);
>  
>  static void __drain_swap_slots_cache(unsigned int type);
> +static void swapcache_async_free_entries(struct work_struct *data);
>  
>  #define use_swap_slot_cache (swap_slot_cache_active && swap_slot_cache_enabled)
>  #define SLOTS_CACHE 0x1
> @@ -149,6 +150,7 @@ static int alloc_swap_slot_cache(unsigned int cpu)
>  		spin_lock_init(&cache->free_lock);
>  		cache->lock_initialized = true;
>  	}
> +	INIT_WORK(&cache->async_free, swapcache_async_free_entries);
>  	cache->nr = 0;
>  	cache->cur = 0;
>  	cache->n_ret = 0;
> @@ -269,12 +271,27 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
>  	return cache->nr;
>  }
>  
> +static void swapcache_async_free_entries(struct work_struct *data)
> +{
> +	struct swap_slots_cache *cache;
> +
> +	cache = container_of(data, struct swap_slots_cache, async_free);
> +	spin_lock_irq(&cache->free_lock);
> +	/* Swap slots cache may be deactivated before acquiring lock */
> +	if (cache->slots_ret && cache->n_ret) {
> +		swapcache_free_entries(cache->slots_ret, cache->n_ret);
> +		cache->n_ret = 0;
> +	}
> +	spin_unlock_irq(&cache->free_lock);
> +}
> +
>  void free_swap_slot(swp_entry_t entry)
>  {
>  	struct swap_slots_cache *cache;
>  
>  	cache = raw_cpu_ptr(&swp_slots);
>  	if (likely(use_swap_slot_cache && cache->slots_ret)) {
> +		bool full;
>  		spin_lock_irq(&cache->free_lock);
>  		/* Swap slots cache may be deactivated before acquiring lock */
>  		if (!use_swap_slot_cache || !cache->slots_ret) {
> @@ -292,7 +309,10 @@ void free_swap_slot(swp_entry_t entry)
>  			cache->n_ret = 0;
>  		}
>  		cache->slots_ret[cache->n_ret++] = entry;
> +		full = cache->n_ret >= SWAP_SLOTS_CACHE_SIZE;
>  		spin_unlock_irq(&cache->free_lock);
> +		if (full)
> +			schedule_work(&cache->async_free);
>  	} else {
>  direct_free:
>  		swapcache_free_entries(&entry, 1);
> 
> ---
> base-commit: eacce8189e28717da6f44ee492b7404c636ae0de
> change-id: 20231216-async-free-bef392015432
> 
> Best regards,